Integrated Sensing, Computing and Semantic Communication for Vehicular Networks

This paper introduces a novel framework for integrated sensing, computing, and semantic communication (ISCSC) within vehicular networks comprising a roadside unit (RSU) and multiple autonomous vehicles. Both the RSU and the vehicles are equipped with local knowledge bases to facilitate semantic communication. The framework incorporates a secure communication design to ensure that messages intended for specific vehicles are protected against interception. Within this model, an extended Kalman filter (EKF) is employed by the RSU to track all vehicles accurately. We formulate a joint optimisation problem that balances maximising the probabilistic-constrained semantic secrecy rate for each vehicle while minimising the sum of the posterior Cramér-Rao bound (PCRB), constrained by the RSU's computing capabilities. This non-convex optimisation problem is addressed using Bernstein-type inequality (BTI) and alternating optimisation (AO) techniques. Simulation results validate the effectiveness of the proposed framework, highlighting its advantages in reliable sensing, high data throughput, and secure communication.